17 April 2018

This summer, Swedish researchers will gain access to significantly higher computing power when the most powerful computer in the Nordic region, Tetralith, is installed at the National Supercomputer Centre, NSC, at Linköping University. The maximum speed of the supercomputer is estimated to exceed 4 petaflops, or 4 000 000 000 000 000 floating point operations per second.

This gives Tetralith a much greater computing power than its predecessor Triolith, which after its expansion in October 2013 held the Nordic record for computing power at 0.45 petaflops.

Tetralith will be a national resource, and all researchers in Sweden will be able to apply for computing time through the Swedish National Infrastructure for Computing, SNIC. The National Supercomputer Centre at LiU is one of six supercomputer centres in Sweden.

Large scale computing evermore important

“Tetralith will be the most powerful university computer in Sweden by a large margin, nearly twice as fast as the next most powerful, at KTH. I’m really looking forward to allocating time on the new computer to the best Swedish researchers and their fascinating projects. It’s very gratifying to see that Sweden is investing heavily in remaining at the forefront of providing computer resources,” says Philipp Schlatter, docent at KTH and chair of the SNIC resource allocation committee.

He continues: “Large scale computing has become evermore important, for both research and development. Tetralith will make a huge contribution, and enable scientists to produce new results within chemistry, biology, materials science, physics, fluid dynamics, climate research, and many other fields. The power required to give this amazing number of four thousand million million calculations per second will be invaluable, and make a huge difference to researchers.”

Funded by SNIC

Approximately SEK 150 million for Tetralith’s funding comes from the SNIC, where half of the money is from the ten universities that are members of SNIC and the other half from the Swedish Research Council.

“Tetralith will be a key resource for Swedish research, and this is the first time such an investment has come exclusively from the SNIC consortium,” says Hans Karlsson, professor at Uppsala University and SNIC’s director.

The need for heavy computing power has increased markedly in recent years and is continuing to increase. New groups of users are appearing all the time.

“We see an increase in the need for computing power in all fields, not just traditional users of supercomputers. New areas such as machine learning and artificial intelligence require increasing amounts of computing power,” says Matts Karlsson, professor at Linköping University and director of NSC.

Intel inside

The new supercomputer is being delivered by Dutch company ClusterVision and is based on processor technology and fast interconnections from Intel. When complete, the system will consist of 1892 servers, with 32 cores each, making a total of 60,544 processor cores. Triolith will be progressively dismantled as the new servers are installed, and the first stage of Tetralith will be brought online on 1 August. The entire installation should be completed by November 2018, when Swedish researchers will gain access to four times the computing power they have had from the current Triolith.

“We plan to make the change-over as smooth as possible for all SNIC users,” Niclas Andersson, technical director at NSC assures us.

Translation: George Farrants

Contact

Latest news from LiU

Server room and data on black background.

Machine Psychology – a bridge to general AI

AI that is as intelligent as humans may become possible thanks to psychological learning models, combined with certain types of AI. This is the conclusion of Robert Johansson, who in his dissertation has developed the concept of Machine Psychology.

Research for a sustainable future awarded almost SEK 20 million grant

An unexpected collaboration between materials science and behavioural science. The development of better and more useful services to tackle climate change. Two projects at LiU are to receive support from the Marianne and Marcus Wallenberg Foundation.

Innovative idea for more effective cancer treatments rewarded

Lisa Menacher has been awarded the 2024 Christer Gilén Scholarship in statistics and machine learning for her master’s thesis. She utilised machine learning in an effort to make the selection of cancer treatments more effective.